INDEX

Explanations

references to planning and proposals for future actions

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

.gdx

-0.16

cela

-0.15

achi

-0.15

ãĤ¹ãĤ«

-0.15

cul

-0.15

éĩı

-0.15

Ã¤lt

-0.15

PlainText

-0.14

ieme

-0.14

/down

-0.14

POSITIVE LOGITS

ayout

0.17

etary

0.17

-ahead

0.16

matic

0.15

ck

0.15

elli

0.15

owski

0.15

isphere

0.15

atics

0.15

ning

0.14

Activations Density 0.065%

references to planning and proposals for future actions

No Comments

No Known Activations